Intel Pushes Ai Reference Kits To Help Sell Its Silicon

Intel has released 34 open source reference kits to reduce the time and resources needed to deploy machine learning systems on its hardware. The kits contain model code, training data, libraries, openAPI components, and instructions to implement them on Intel hardware. Intel has a variety of accelerators and GPUs capable of running AI applications, such as Habana Gaudi2 training processors, Ponte Vecchio GPUs, and the Advanced Matrix Extensions. These kits may help Intel score wins due to the large clusters of GPU nodes required to train the largest models, as Nvidia’s GPUs have been selling for high prices on eBay.